Back to models
Intelligence Index
Reasoning setting
15.6#58 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 524.29K tok
Performance profile
ReasoningRank #78 of 107
69.2%
GPQA DiamondCodingRank #88 of 94
22.0%
SciCodeCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)Reasoning
- Intelligence Index
- 15.6
Pricing & access
No API offering listed in our tracked sources.
Run locally
- Original download
- 10.1 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)13.9%, rank 79 of 12622.0%, rank 88 of 940.0%, rank 56 of 8762.3%, rank 79 of 125882 Elo, rank 57 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 76Gemma 4 12BReasoning15.7%
- 77Qwen3.5 9BReasoning14.9%
- 78Qwen3.5 Omni PlusStandard14.9%
- 79K2 Horizon 3.7BReasoning13.9%
- 80Mistral Medium 3.5High13.8%
- 81EXAONE 4.5 33BReasoning12.9%
- 82Qwen3 Next 80B A3B (Reasoning)Reasoning12.6%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherRing-2.6-1TExtra high
- Intelligence Index
- 16.6+1.0
- Cost / task
- $0.287
- More from Institute of Foundation ModelsK2 Horizon 7BReasoning
- Intelligence Index
- 20.6+5.0
- Similar scoreQwen3.5 122B A10BReasoning
- Intelligence Index
- 15.6−0.0
- Cost / task
- $0.325
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.